© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97711
    Prev
    Next
    INDEX
    Explanations

    generate/produce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.71
    PerformLayout
    -0.64
    acağı
    -0.62
     suicidio
    -0.56
     numerus
    -0.55
    ंदीखरीदारी
    -0.54
     prostitu
    -0.53
     confort
    -0.52
    ardige
    -0.52
     venda
    -0.52
    POSITIVE LOGITS
    RegistryLite
    0.59
     $("<
    0.53
     figures
    0.52
     AssemblyCompany
    0.52
    razos
    0.51
    anskje
    0.51
    tymologie
    0.49
    ENODEV
    0.49
    itattu
    0.48
     $('<
    0.48
    Activations Density 0.111%

    No Known Activations